Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching

Documenti analoghi

• PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning
  di: Liu, Zhuoyao, et al.
  Pubblicazione: (2025)
• Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
  di: Liu, Yang, et al.
  Pubblicazione: (2025)
• Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval
  di: Wang, Yifan, et al.
  Pubblicazione: (2025)
• Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching
  di: Liu, Yuhan, et al.
  Pubblicazione: (2025)
• DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching
  di: Huang, Ranran, et al.
  Pubblicazione: (2022)